This demo shows you how to generate multimodal embeddings by passing
multimodal input, such as text and an image to an embedding model, by
using the Vertex AI SDK for ABAP.
Before you begin
Before you run this demo, make sure that you or your administrators have
completed the following prerequisites:
Configured the model generation parameters. For generating embeddings, only the following
parameters are required: Client Key, Model Key, Model ID,
Google Cloud Region Location and Publisher.
Generate multimodal embeddings
To generate multimodal embeddings, perform the following steps:
In SAP GUI, execute the transaction code /GOOG/SDK_IMG.
Alternatively, execute the transaction code SPRO, and then click SAP Reference IMG.
Go to ABAP SDK for Google Cloud > Demos.
Open Demo: Invoke multimodal Embedding models
Select Generate multimodal embeddings.
In the Client key field, enter the client key for authentication.
In the Dimensions field, enter the number of dimensions for the output embeddings,
such as 1408. For multimodal
embeddings, the available dimensions are: 128, 256, 512, and 1408.
Specify values for the following fields as appropriate:
GCS URI of image: To add an image to your request, specify the URI
of the image stored in a Cloud Storage bucket.
Upload image: To add an image to your request, upload the image
from your local system.
GCS URI of video: To add a video to your request, specify the URI
of the video stored in a Cloud Storage bucket.
You can either specify the URI of a file from Cloud Storage
or upload a file from your local system.
In the Enter text field, provide your input text.
Run the program. The Response from LLM area shows the generated embeddings.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Demo: Generate multimodal embeddings\n\n\u003cbr /\u003e\n\nThis demo shows you how to generate multimodal embeddings by passing\nmultimodal input, such as text and an image to an embedding model, by\nusing the Vertex AI SDK for ABAP.\n\n\n| **Note:** Demo programs are available only with the on-premises or any cloud edition of ABAP SDK for Google Cloud. They are not available with the SAP BTP edition of ABAP SDK for Google Cloud.\n\n\u003cbr /\u003e\n\nBefore you begin\n----------------\n\nBefore you run this demo, make sure that you or your administrators have\ncompleted the following prerequisites:\n\n- [Enabled the Vertex AI API](/sap/docs/abap-sdk/vertex-ai-sdk/latest/install-configure-vertex-ai-sdk-abap#enable-api) in your Google Cloud project.\n- [Set up authentication](/sap/docs/abap-sdk/vertex-ai-sdk/latest/install-configure-vertex-ai-sdk-abap#authentication) to access the Vertex AI API.\n- [Configured the model generation parameters](/sap/docs/abap-sdk/vertex-ai-sdk/latest/install-configure-vertex-ai-sdk-abap#configure-model-generation-parameters). For generating embeddings, only the following parameters are required: `Client Key`, `Model Key`, `Model ID`, `Google Cloud Region Location` and `Publisher`.\n\nGenerate multimodal embeddings\n------------------------------\n\nTo generate multimodal embeddings, perform the following steps:\n\n1.\n In SAP GUI, execute the transaction code `/GOOG/SDK_IMG`.\n\n Alternatively, execute the transaction code `SPRO`, and then click **SAP Reference IMG**.\n\n \u003cbr /\u003e\n\n2. Go to **ABAP SDK for Google Cloud \\\u003e Demos**.\n\n3. Open **Demo: Invoke multimodal Embedding models**\n\n4. Select **Generate multimodal embeddings**.\n\n5. In the **Client key** field, enter the client key for authentication.\n\n6. In the **Model key** field, enter the model key, which is configured in the [model generation parameters](/sap/docs/abap-sdk/vertex-ai-sdk/latest/install-configure-vertex-ai-sdk-abap#configure-model-generation-parameters).\n\n7. In the **Dimensions** field, enter the number of dimensions for the output embeddings,\n such as `1408`. For multimodal\n embeddings, the available dimensions are: `128`, `256`, `512`, and `1408`.\n\n8. Specify values for the following fields as appropriate:\n\n - **GCS URI of image**: To add an image to your request, specify the URI of the image stored in a Cloud Storage bucket.\n - **Upload image**: To add an image to your request, upload the image from your local system.\n - **GCS URI of video**: To add a video to your request, specify the URI of the video stored in a Cloud Storage bucket.\n\n You can either specify the URI of a file from Cloud Storage\n or upload a file from your local system.\n9. In the **Enter text** field, provide your input text.\n\n10. Run the program. The **Response from LLM** area shows the generated embeddings."]]
